SharkCraft importer: parse AGENTS.md / CLAUDE.md / .cursor/rules into structured knowledge entries.
SuPi claude-md extension — automatic subdirectory context injection for pi
Grade any AI instruction file from your terminal: does it load, read clearly, stay safe, and behave consistently across every model and tool. Plus install, convert, and bundle skills, instructions, and Tomes for any AI coding tool.
Architecture rules your AI coding agent can't ignore. It gets the rules for a file before it edits, and every change is checked — by a free local script or an LLM reviewer — before it moves on. Works with Claude Code, Cursor, Copilot, Codex, Cline.
One-command, self-updating onboarding for Xmarts Genius (Brain MCP + per-turn injection + automatic session/time capture + presence heartbeat for honest time-tracking 'amarre' + plan/committee→Brain enforcement + CLAUDE.md protocol + MCP fan-out: provisio
Scaffold AI conventions (CLAUDE.md) into your project
Autonomous AI agent memory system with CLAUDE.md protocol enforcement
One command to configure Claude Code for any project: detects stack, installs MCPs, writes CLAUDE.md.
Reflect — automated CLAUDE.md collaboration profiles. Diagnoses instruction compliance issues backed by empirical research.
ctrlai — your Context Key, in one command. npx @ctrlai/cli init writes CLAUDE.md / .cursorrules / AGENTS.md from one source (no account, nothing leaves your machine); also emit, fetch ready-to-inject context, and seed your self from a repo. A thin clien
AI agent integration plugin for Baseplate — generates AGENTS.md, CLAUDE.md, .mcp.json, and .agents/ configuration files
Define an AI agent once, generate the config file every tool expects (CLAUDE.md, AGENTS.md). Implements the AGENTS.md standard. Prior art: open-gitagent (MIT).
Bottari team's portable Claude Code skills (spec, spec-review, boss, decide, e2e, distill-doc). Vendors skills into a repo's .claude/skills and wires the always-on playbook (dev principles + loop) into CLAUDE.md.
Static, offline audit of your Claude Code setup — flags never-used MCP connectors, oversized CLAUDE.md/memory, and missing context guardrails. Then lays down a lean default setup.